© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 1-RES-SM
    11. 26192
    Prev
    Next
    INDEX
    Explanations

    references to poison and its related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/1-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    369
    +0.15
    0.8%
    410
    +0.12
    0.7%
    350
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    49
    +0.15
    0.02
    2
    +0.12
    0.02
    476
    +0.12
    0.02
    Negative Logits
     forehead
    -1.75
     normal
    -1.65
     resolutions
    -1.62
    oscope
    -1.55
     periods
    -1.51
    frastructure
    -1.50
     proposed
    -1.47
     course
    -1.46
    lasses
    -1.45
     horizon
    -1.45
    POSITIVE LOGITS
    inters
    2.32
    inte
    2.09
    ppo
    2.06
    ppa
    1.98
    ¾
    1.90
    ître
    1.84
    ppers
    1.82
    isons
    1.74
    ilage
    1.74
    wn
    1.74
    Activations Density 0.090%

    No Known Activations